The scarcity of in-situ ocean observations poses a challenge for real-time information acquisition in the ocean.Among the crucial hydroacoustic environmental parameters,ocean sound velocity exhibits significant spatia...The scarcity of in-situ ocean observations poses a challenge for real-time information acquisition in the ocean.Among the crucial hydroacoustic environmental parameters,ocean sound velocity exhibits significant spatial and temporal variability and it is highly relevant to oceanic research.In this study,we propose a new data-driven approach,leveraging deep learning techniques,for the prediction of sound velocity fields(SVFs).Our novel spatiotemporal prediction model,STLSTM-SA,combines Spatiotemporal Long Short-Term Memory(ST-LSTM) with a self-attention mechanism to enable accurate and real-time prediction of SVFs.To circumvent the limited amount of observational data,we employ transfer learning by first training the model using reanalysis datasets,followed by fine-tuning it using in-situ analysis data to obtain the final prediction model.By utilizing the historical 12-month SVFs as input,our model predicts the SVFs for the subsequent three months.We compare the performance of five models:Artificial Neural Networks(ANN),Long ShortTerm Memory(LSTM),Convolutional LSTM(ConvLSTM),ST-LSTM,and our proposed ST-LSTM-SA model in a test experiment spanning 2019 to 2022.Our results demonstrate that the ST-LSTM-SA model significantly improves the prediction accuracy and stability of sound velocity in both temporal and spatial dimensions.The ST-LSTM-SA model not only accurately predicts the ocean sound velocity field(SVF),but also provides valuable insights for spatiotemporal prediction of other oceanic environmental variables.展开更多
Traffic flow prediction is an important component of intelligent transportation systems.Recently,unprecedented data availability and rapid development of machine learning techniques have led to tremendous progress in ...Traffic flow prediction is an important component of intelligent transportation systems.Recently,unprecedented data availability and rapid development of machine learning techniques have led to tremendous progress in this field.This article first introduces the research on traffic flow prediction and the challenges it currently faces.It then proposes a classification method for literature,discussing and analyzing existing research on using machine learning methods to address traffic flow prediction from the perspectives of the prediction preparation process and the construction of prediction models.The article also summarizes innovative modules in these models.Finally,we provide improvement strategies for current baseline models and discuss the challenges and research directions in the field of traffic flow prediction in the future.展开更多
Traffic flow prediction becomes an essential process for intelligent transportation systems(ITS).Though traffic sensor devices are manually controllable,traffic flow data with distinct length,uneven sampling,and missi...Traffic flow prediction becomes an essential process for intelligent transportation systems(ITS).Though traffic sensor devices are manually controllable,traffic flow data with distinct length,uneven sampling,and missing data finds challenging for effective exploitation.The traffic data has been considerably increased in recent times which cannot be handled by traditional mathematical models.The recent developments of statistic and deep learning(DL)models pave a way for the effectual design of traffic flow prediction(TFP)models.In this view,this study designs optimal attentionbased deep learning with statistical analysis for TFP(OADLSA-TFP)model.The presentedOADLSA-TFP model intends to effectually forecast the level of traffic in the environment.To attain this,the OADLSA-TFP model employs attention-based bidirectional long short-term memory(ABLSTM)model for predicting traffic flow.In order to enhance the performance of the ABLSTM model,the hyperparameter optimization process is performed using artificial fish swarm algorithm(AFSA).A wide-ranging experimental analysis is carried out on benchmark dataset and the obtained values reported the enhancements of the OADLSA-TFP model over the recent approaches mean square error(MSE),root mean square error(RMSE),and mean absolute percentage error(MAPE)of 120.342%,10.970%,and 8.146%respectively.展开更多
Artificial intelligence technology is introduced into the simulation of muzzle flow field to improve its simulation efficiency in this paper.A data-physical fusion driven framework is proposed.First,the known flow fie...Artificial intelligence technology is introduced into the simulation of muzzle flow field to improve its simulation efficiency in this paper.A data-physical fusion driven framework is proposed.First,the known flow field data is used to initialize the model parameters,so that the parameters to be trained are close to the optimal value.Then physical prior knowledge is introduced into the training process so that the prediction results not only meet the known flow field information but also meet the physical conservation laws.Through two examples,it is proved that the model under the fusion driven framework can solve the strongly nonlinear flow field problems,and has stronger generalization and expansion.The proposed model is used to solve a muzzle flow field,and the safety clearance behind the barrel side is divided.It is pointed out that the shape of the safety clearance under different launch speeds is roughly the same,and the pressure disturbance in the area within 9.2 m behind the muzzle section exceeds the safety threshold,which is a dangerous area.Comparison with the CFD results shows that the calculation efficiency of the proposed model is greatly improved under the condition of the same calculation accuracy.The proposed model can quickly and accurately simulate the muzzle flow field under various launch conditions.展开更多
Accurate and real-time passenger flow prediction of rail transit is an important part of intelligent transportation systems(ITS).According to previous studies,it is found that the prediction effect of a single model i...Accurate and real-time passenger flow prediction of rail transit is an important part of intelligent transportation systems(ITS).According to previous studies,it is found that the prediction effect of a single model is not good for datasets with large changes in passenger flow characteristics and the deep learning model with added influencing factors has better prediction accuracy.In order to provide persuasive passenger flow forecast data for ITS,a deep learning model considering the influencing factors is proposed in this paper.In view of the lack of objective analysis on the selection of influencing factors by predecessors,this paper uses analytic hierarchy processes(AHP)and one-way ANOVA analysis to scientifically select the factor of time characteristics,which classifies and gives weight to the hourly passenger flow through Duncan test.Then,combining the time weight,BILSTM based model considering the hourly travel characteristics factors is proposed.The model performance is verified through the inbound passenger flow of Ningbo rail transit.The proposed model is compared with many current mainstream deep learning algorithms,the effectiveness of the BILSTM model considering influencing factors is validated.Through comparison and analysis with various evaluation indicators and other deep learning models,the results show that the R2 score of the BILSTM model considering influencing factors reaches 0.968,and the MAE value of the BILSTM model without adding influencing factors decreases by 45.61%.展开更多
In order to improve the accuracy and stability of terminal traffic flow prediction in convective weather,a multi-input deep learning(MICL)model is proposed.On the basis of previous studies,this paper expands the set o...In order to improve the accuracy and stability of terminal traffic flow prediction in convective weather,a multi-input deep learning(MICL)model is proposed.On the basis of previous studies,this paper expands the set of weather characteristics affecting the traffic flow in the terminal area,including weather forecast data and Meteorological Report of Aerodrome Conditions(METAR)data.The terminal airspace is divided into smaller areas based on function and the weather severity index(WSI)characteristics extracted from weather forecast data are established to better quantify the impact of weather.MICL model preserves the advantages of the convolution neural network(CNN)and the long short-term memory(LSTM)model,and adopts two channels to input WSI and METAR information,respectively,which can fully reflect the temporal and spatial distribution characteristics of weather in the terminal area.Multi-scene experiments are designed based on the real historical data of Guangzhou Terminal Area operating in typical convective weather.The results show that the MICL model has excellent performance in mean squared error(MSE),root MSE(RMSE),mean absolute error(MAE)and other performance indicators compared with the existing machine learning models or deep learning models,such as Knearest neighbor(KNN),support vector regression(SVR),CNN and LSTM.In the forecast period ranging from 30 min to 6 h,the MICL model has the best prediction accuracy and stability.展开更多
Predicting traffic flow is a crucial component of an intelligent transportation system.Precisely monitoring and predicting traffic flow remains a challenging endeavor.However,existingmethods for predicting traffic flo...Predicting traffic flow is a crucial component of an intelligent transportation system.Precisely monitoring and predicting traffic flow remains a challenging endeavor.However,existingmethods for predicting traffic flow do not incorporate various external factors or consider the spatiotemporal correlation between spatially adjacent nodes,resulting in the loss of essential information and lower forecast performance.On the other hand,the availability of spatiotemporal data is limited.This research offers alternative spatiotemporal data with three specific features as input,vehicle type(5 types),holidays(3 types),and weather(10 conditions).In this study,the proposed model combines the advantages of the capability of convolutional(CNN)layers to extract valuable information and learn the internal representation of time-series data that can be interpreted as an image,as well as the efficiency of long short-term memory(LSTM)layers for identifying short-term and long-term dependencies.Our approach may utilize the heterogeneous spatiotemporal correlation features of the traffic flowdataset to deliver better performance traffic flow prediction than existing deep learning models.The research findings show that adding spatiotemporal feature data increases the forecast’s performance;weather by 25.85%,vehicle type by 23.70%,and holiday by 14.02%.展开更多
According to the time series characteristics of the trajectory history data,we predicted and analyzed the traffic flow.This paper proposed a LSTMXGBoost model based urban road short-term traffic flow prediction in ord...According to the time series characteristics of the trajectory history data,we predicted and analyzed the traffic flow.This paper proposed a LSTMXGBoost model based urban road short-term traffic flow prediction in order to analyze and solve the problems of periodicity,stationary and abnormality of time series.It can improve the traffic flow prediction effect,achieve efficient traffic guidance and traffic control.The model combined the characteristics of LSTM(Long Short-Term Memory)network and XGBoost(Extreme Gradient Boosting)algorithms.First,we used the LSTM model that increases dropout layer to train the data set after preprocessing.Second,we replaced the full connection layer with the XGBoost model.Finally,we depended on the model training to strengthen the data association,avoided the overfitting phenomenon of the fully connected layer,and enhanced the generalization ability of the prediction model.We used the Kears based on TensorFlow to build the LSTM-XGBoost model.Using speed data samples of multiple road sections in Shenzhen to complete the model verification,we achieved the comparison of the prediction effects of the model.The results show that the combined prediction model used in this paper can not only improve the accuracy of prediction,but also improve the practicability,real-time and scalability of the model.展开更多
Aiming at the problem that some existing traffic flow prediction models are only for a single road segment and the model input data are not pre-processed,a heuristic threshold algorithm is used to de-noise the origina...Aiming at the problem that some existing traffic flow prediction models are only for a single road segment and the model input data are not pre-processed,a heuristic threshold algorithm is used to de-noise the original traffic flow data after wavelet decomposition.The correlation coefficients of road traffic flow data are calculated and the data compression matrix of road traffic flow is constructed.Data de-noising minimizes the interference of data to the model,while the correlation analysis of road network data realizes the prediction at the road network level.Utilizing the advantages of long short term memory(LSTM)network in time series data processing,the compression matrix is input into the constructed LSTM model for short-term traffic flow prediction.The LSTM-1 and LSTM-2 models were respectively trained by de-noising processed data and original data.Through simulation experiments,different prediction times were set,and the prediction results of the prediction model proposed in this paper were compared with those of other methods.It is found that the accuracy of the LSTM-2 model proposed in this paper increases by 10.278%on average compared with other prediction methods,and the prediction accuracy reaches 95.58%,which proves that the short-term traffic flow prediction method proposed in this paper is efficient.展开更多
Intelligent Transportation System(ITS)is one of the revolutionary technologies in smart cities that helps in reducing traffic congestion and enhancing traffic quality.With the help of big data and communication techno...Intelligent Transportation System(ITS)is one of the revolutionary technologies in smart cities that helps in reducing traffic congestion and enhancing traffic quality.With the help of big data and communication technologies,ITS offers real-time investigation and highly-effective traffic management.Traffic Flow Prediction(TFP)is a vital element in smart city management and is used to forecast the upcoming traffic conditions on transportation network based on past data.Neural Network(NN)and Machine Learning(ML)models are widely utilized in resolving real-time issues since these methods are capable of dealing with adaptive data over a period of time.Deep Learning(DL)is a kind of ML technique which yields effective performance on data classification and prediction tasks.With this motivation,the current study introduces a novel Slime Mould Optimization(SMO)model with Bidirectional Gated Recurrent Unit(BiGRU)model for Traffic Prediction(SMOBGRU-TP)in smart cities.Initially,data preprocessing is performed to normalize the input data in the range of[0,1]using minmax normalization approach.Besides,BiGRUmodel is employed for effective forecasting of traffic in smart cities.Moreover,the novelty of the work lies in using SMO algorithm to effectively adjust the hyperparameters of BiGRU method.The proposed SMOBGRU-TP model was experimentally validated and the simulation results established the model’s superior performance in terms of prediction compared to existing techniques.展开更多
Mathematical(data-driven)models based on state-of-the-art(SOTA)machine learning and deep learning models and data collected from 12,786 heats were established to predict the values of temperature,sample,and carbon(TSC...Mathematical(data-driven)models based on state-of-the-art(SOTA)machine learning and deep learning models and data collected from 12,786 heats were established to predict the values of temperature,sample,and carbon(TSC)test,including temperature of molten steel(TSC-Temp),carbon content(TSC-C)and phosphorus content(TSC-P),which made prepa-ration for eliminating the TSC test.To maximize the prediction accuracy of the proposed approach,various models with different inputs were implemented and compared,and the best models were applied to the production process of a Hesteel Group steelmaking plant in China in the field.The number of tabular features(hot metal information,scrap,additives,blowing practices,and preset values)was expanded,and time series(off-gas profiles and blowing practice curves)that could reflect the entire steelmaking process were introduced as inputs.First,the latest machine learning models(LightGBM,CatBoost,TabNet,and NODE)were used to make predictions with tabular features,and the best coefficient of determination R^(2)values obtained for TSC-P,TSC-C and TSC-Temp predictions were 0.435(LightGBM),0.857(Cat-Boost)and 0.678(LightGBM),respectively,which were higher than those of classic models(backpropagation and support vector machine).Then,making predictions was performed by using SOTA time series regression models(SCINet,DLinear,Informer,and MLSTM-FCN)with original time series,SOTA image regression models(NesT,CaiT,ResNeXt,and GoogLeNet)with resized time series,and the proposed Concatenate-Model and Parallel-Model with both tabular features and time series.Through optimization and comparisons,it was finally determined that the Concatenate-Model with MLSTM-FCN,SCINet and Informer as feature extractors performed the best,and its R^(2)values for predicting TSC-P,TSC-C and TSC-Temp reached 0.470,0.858 and 0.710,respectively.Its field test accuracies for TSC-P,TSC-C and TSC-Temp were 0.459,0.850 and 0.685,respectively.A related importance analysis was carried out,and dynamic control methods based on prediction values were proposed.展开更多
The airborne base station(ABS) can provide wireless coverage to the ground in unmanned aerial vehicle(UAV) cellular networks.When mobile users move among adjacent ABSs,the measurement information reported by a single ...The airborne base station(ABS) can provide wireless coverage to the ground in unmanned aerial vehicle(UAV) cellular networks.When mobile users move among adjacent ABSs,the measurement information reported by a single mobile user is used to trigger the handover mechanism.This handover mechanism lacks the consideration of movement state of mobile users and the location relationship between mobile users,which may lead to handover misjudgments and even communication interrupts.In this paper,we propose an intelligent handover control method in UAV cellular networks.Firstly,we introduce a deep learning model to predict the user trajectories.This prediction model learns the movement behavior of mobile users from the measurement information and analyzes the positional relations between mobile users such as avoiding collision and accommodating fellow pedestrians.Secondly,we propose a handover decision method,which can calculate the users' corresponding receiving power based on the predicted location and the characteristic of air-to-ground channel,to make handover decisions accurately.Finally,we use realistic data sets with thousands of non-linear trajectories to verify the basic functions and performance of our proposed intelligent handover controlmethod.The simulation results show that the handover success rate of the proposed method is 8% higher than existing methods.展开更多
To accurately analyze the fluctuation range of time-varying differences in metro-to-bus transfer passenger flows,the application of a probabilistic interval prediction model is proposed to predict transfer passenger f...To accurately analyze the fluctuation range of time-varying differences in metro-to-bus transfer passenger flows,the application of a probabilistic interval prediction model is proposed to predict transfer passenger flows.First,bus and metro data are processed and matched by association to construct the basis for public transport trip chain extraction.Second,a reasonable matching threshold method to discriminate the transfer relationship is used to extract the public transport trip chain,and the basic characteristics of the trip based on the trip chain are analyzed to obtain the metro-to-bus transfer passenger flow.Third,to address the problem of low accuracy of point prediction,the DeepAR model is proposed to conduct interval prediction,where the input is the interchange passenger flow,the output is the predicted median and interval of passenger flow,and the prediction scenarios are weekday,non-workday,and weekday morning and evening peaks.Fourth,to reduce the prediction error,a combined particle swarm optimization(PSO)-DeepAR model is constructed using the PSO to optimize the DeepAR model.Finally,data from the Beijing Xizhimen subway station are used for validation,and results show that the PSO-DeepAR model has high prediction accuracy,with a 90%confidence interval coverage of up to 93.6%.展开更多
Cooperative Intelligent Transport System(C-ITS)plays a vital role in the future road traffic management system.A vital element of C-ITS comprises vehicles,road side units,and traffic command centers,which produce a ma...Cooperative Intelligent Transport System(C-ITS)plays a vital role in the future road traffic management system.A vital element of C-ITS comprises vehicles,road side units,and traffic command centers,which produce a massive quantity of data comprising both mobility and service-related data.For the extraction of meaningful and related details out of the generated data,data science acts as an essential part of the upcoming C-ITS applications.At the same time,prediction of short-term traffic flow is highly essential to manage the traffic accurately.Due to the rapid increase in the amount of traffic data,deep learning(DL)models are widely employed,which uses a non-parametric approach for dealing with traffic flow forecasting.This paper focuses on the design of intelligent deep learning based short-termtraffic flow prediction(IDL-STFLP)model for C-ITS that assists the people in various ways,namely optimization of signal timing by traffic signal controllers,travelers being able to adapt and alter their routes,and so on.The presented IDLSTFLP model operates on two main stages namely vehicle counting and traffic flow prediction.The IDL-STFLP model employs the Fully Convolutional Redundant Counting(FCRC)based vehicle count process.In addition,deep belief network(DBN)model is applied for the prediction of short-term traffic flow.To further improve the performance of the DBN in traffic flow prediction,it will be optimized by Quantum-behaved bat algorithm(QBA)which optimizes the tunable parameters of DBN.Experimental results based on benchmark dataset show that the presented method can count vehicles and predict traffic flowin real-time with amaximumperformance under dissimilar environmental situations.展开更多
In this study, potential of Least Square-Support Vector Regression (LS-SVR) approach is utilized to model the daily variation of river flow. Inherent complexity, unavailability of reasonably long data set and heteroge...In this study, potential of Least Square-Support Vector Regression (LS-SVR) approach is utilized to model the daily variation of river flow. Inherent complexity, unavailability of reasonably long data set and heterogeneous catchment response are the couple of issues that hinder the generalization of relationship between previous and forthcoming river flow magnitudes. The problem complexity may get enhanced with the influence of upstream dam releases. These issues are investigated by exploiting the capability of LS-SVR–an approach that considers Structural Risk Minimization (SRM) against the Empirical Risk Minimization (ERM)–used by other learning approaches, such as, Artificial Neural Network (ANN). This study is conducted in upper Narmada river basin in India having Bargi dam in its catchment, constructed in 1989. The river gauging station–Sandia is located few hundred kilometer downstream of Bargi dam. The model development is carried out with pre-construction flow regime and its performance is checked for both pre- and post-construction of the dam for any perceivable difference. It is found that the performances are similar for both the flow regimes, which indicates that the releases from the dam at daily scale for this gauging site may be ignored. In order to investigate the temporal horizon over which the prediction performance may be relied upon, a multistep-ahead prediction is carried out and the model performance is found to be reasonably good up to 5-day-ahead predictions though the performance is decreasing with the increase in lead-time. Skills of both LS-SVR and ANN are reported and it is found that the former performs better than the latter for all the lead-times in general, and shorter lead times in particular.展开更多
Traffic flow prediction is an effective strategy to assess traffic conditions and alleviate traffic congestion. Influenced by external non-stationary factors and road network structure, traffic flow sequences have mac...Traffic flow prediction is an effective strategy to assess traffic conditions and alleviate traffic congestion. Influenced by external non-stationary factors and road network structure, traffic flow sequences have macro spatiotemporal characteristics and micro chaotic characteristics. The key to improving the model prediction accuracy is to fully extract the macro and micro characteristics of traffic flow time sequences. However, traditional prediction model by only considers time features of traffic data, ignoring spatial characteristics and nonlinear characteristics of the data itself, resulting in poor model prediction performance. In view of this, this research proposes an intelligent combination prediction model taking into account the macro and micro features of chaotic traffic data. Firstly, to address the problem of time-consuming and inefficient multivariate phase space reconstruction by iterating nodes one by one, an improved multivariate phase space reconstruction method is proposed by filtering global representative nodes to effectively realize the high-dimensional mapping of chaotic traffic flow. Secondly, to address the problem that the traditional combinatorial model is difficult to adequately learn the macro and micro characteristics of chaotic traffic data, a combination of convolutional neural network(CNN) and convolutional long short-term memory(ConvLSTM) is utilized for capturing nonlinear features of traffic flow more comprehensively. Finally,to overcome the challenge that the combined model performance degrades due to subjective empirical determined network parameters, an improved lightweight particle swarm is proposed for improving prediction accuracy by optimizing model hyperparameters. In this paper, two highway datasets collected by the Caltrans Performance Measurement System(PeMS)are taken as the research objects, and the experimental results from multiple perspectives show that the comprehensive performance of the method proposed in this research is superior to those of the prevalent methods.展开更多
Accurate measurements of physical parameters in a scramjet isolator are very important to promote the design and optimization of the isolator and even the scramjet.In a ground experiment,limited by the inherent charac...Accurate measurements of physical parameters in a scramjet isolator are very important to promote the design and optimization of the isolator and even the scramjet.In a ground experiment,limited by the inherent characteristics of measurement technology and equipment,it is a big challenge to obtain the velocity field inside an isolator.In this study,a deep learning approach was introduced to combine data obtained from ground experiments and numerical simulations,and a velocity field prediction model was developed for obtaining the velocity field inside an isolator based on experimental Schlieren images.The velocity field prediction model was designed with convolutional neural networks as the main structure.Ground experiments of a scramjet isolator under continuous Mach number variation were carried out,and Schlieren images of the flow field inside the isolator were collected.Numerical simulations of the isolator were also carried out,and the velocity fields inside the isolator under various Mach numbers were obtained.The velocity field prediction model was trained using flow field datasets containing experimental Schlieren images and velocity field,and the mapping relationship between the experimental Schlieren images and the predicted velocity field was successfully established.展开更多
The high-resolution(HR)spatio-temporal flow field plays a decisive role in describing the details of the flow field.In the acquisition of the HR flow field,traditional direct numerical simulation(DNS)and other methods...The high-resolution(HR)spatio-temporal flow field plays a decisive role in describing the details of the flow field.In the acquisition of the HR flow field,traditional direct numerical simulation(DNS)and other methods face a seriously high computational burden.To address this deficiency,we propose a novel multi-scale temporal path UNet(MST-UNet)model to reconstruct temporal and spatial HR flow fields from low-resolu-tion(LR)flow field data.Different from the previous super-resolution(SR)model,which only takes advantage of LR flow field data at instantaneous(SLR)or in a time-series(MTLR),MST-UNet introduces multi-scale information in both time and space.MST-UNet takes the LR data at the current frame and the predicted HR result at the previous moment as the model input to complete the spatial SR reconstruction.On this basis,a temporal model is introduced as the inbetweening model to obtain HR flow field data in space and time to complete spatio-temporal SR reconstruction.Finally,the proposed model is validated by the spatio-temporal SR task of the flow field around two-dimen-sional cylinders.Experimental results show that the outcome of the MST-UNet model in spatial SR tasks is much better than those of SLR and MTLR,which can greatly improve prediction accuracy.In addition,for the spatio-temporal SR task,the spatio-temporal HR flow field predicted by the MST-UNet model has higher accuracy either.展开更多
Phase unwrapping is one of the key roles in fringe projection three-dimensional(3D)measurement technology.We propose a new method to achieve phase unwrapping in camera array light filed fringe projection 3D measuremen...Phase unwrapping is one of the key roles in fringe projection three-dimensional(3D)measurement technology.We propose a new method to achieve phase unwrapping in camera array light filed fringe projection 3D measurement based on deep learning.A multi-stream convolutional neural network(CNN)is proposed to learn the mapping relationship between camera array light filed wrapped phases and fringe orders of the expected central view,and is used to predict the fringe order to achieve the phase unwrapping.Experiments are performed on the light field fringe projection data generated by the simulated camera array fringe projection measurement system in Blender and by the experimental 3×3 camera array light field fringe projection system.The performance of the proposed network with light field wrapped phases using multiple directions as network input data is studied,and the advantages of phase unwrapping based on deep learning in light filed fringe projection are demonstrated.展开更多
基金supported by the National Natural Science Foundation of China(Grant No.42004030)Basic Scientific Fund for National Public Research Institutes of China(Grant No.2022S03)+1 种基金Science and Technology Innovation Project(LSKJ202205102)funded by Laoshan Laboratory,and the National Key Research and Development Program of China(2020YFB0505805).
文摘The scarcity of in-situ ocean observations poses a challenge for real-time information acquisition in the ocean.Among the crucial hydroacoustic environmental parameters,ocean sound velocity exhibits significant spatial and temporal variability and it is highly relevant to oceanic research.In this study,we propose a new data-driven approach,leveraging deep learning techniques,for the prediction of sound velocity fields(SVFs).Our novel spatiotemporal prediction model,STLSTM-SA,combines Spatiotemporal Long Short-Term Memory(ST-LSTM) with a self-attention mechanism to enable accurate and real-time prediction of SVFs.To circumvent the limited amount of observational data,we employ transfer learning by first training the model using reanalysis datasets,followed by fine-tuning it using in-situ analysis data to obtain the final prediction model.By utilizing the historical 12-month SVFs as input,our model predicts the SVFs for the subsequent three months.We compare the performance of five models:Artificial Neural Networks(ANN),Long ShortTerm Memory(LSTM),Convolutional LSTM(ConvLSTM),ST-LSTM,and our proposed ST-LSTM-SA model in a test experiment spanning 2019 to 2022.Our results demonstrate that the ST-LSTM-SA model significantly improves the prediction accuracy and stability of sound velocity in both temporal and spatial dimensions.The ST-LSTM-SA model not only accurately predicts the ocean sound velocity field(SVF),but also provides valuable insights for spatiotemporal prediction of other oceanic environmental variables.
基金supported by 2022 Shenyang Philosophy and Social Science Planning under grant SY202201Z,Liaoning Provincial Department of Education Project under grant LJKZ0588.
文摘Traffic flow prediction is an important component of intelligent transportation systems.Recently,unprecedented data availability and rapid development of machine learning techniques have led to tremendous progress in this field.This article first introduces the research on traffic flow prediction and the challenges it currently faces.It then proposes a classification method for literature,discussing and analyzing existing research on using machine learning methods to address traffic flow prediction from the perspectives of the prediction preparation process and the construction of prediction models.The article also summarizes innovative modules in these models.Finally,we provide improvement strategies for current baseline models and discuss the challenges and research directions in the field of traffic flow prediction in the future.
基金This project was funded by the Deanship of Scientific Research(DSR)at King Abdulaziz University(KAU),Jeddah,Saudi Arabia,under grant no.(G:665-980-1441).
文摘Traffic flow prediction becomes an essential process for intelligent transportation systems(ITS).Though traffic sensor devices are manually controllable,traffic flow data with distinct length,uneven sampling,and missing data finds challenging for effective exploitation.The traffic data has been considerably increased in recent times which cannot be handled by traditional mathematical models.The recent developments of statistic and deep learning(DL)models pave a way for the effectual design of traffic flow prediction(TFP)models.In this view,this study designs optimal attentionbased deep learning with statistical analysis for TFP(OADLSA-TFP)model.The presentedOADLSA-TFP model intends to effectually forecast the level of traffic in the environment.To attain this,the OADLSA-TFP model employs attention-based bidirectional long short-term memory(ABLSTM)model for predicting traffic flow.In order to enhance the performance of the ABLSTM model,the hyperparameter optimization process is performed using artificial fish swarm algorithm(AFSA).A wide-ranging experimental analysis is carried out on benchmark dataset and the obtained values reported the enhancements of the OADLSA-TFP model over the recent approaches mean square error(MSE),root mean square error(RMSE),and mean absolute percentage error(MAPE)of 120.342%,10.970%,and 8.146%respectively.
基金Supported by the Natural Science Foundation of Jiangsu Province of China(Grant No.BK20210347)Supported by the National Natural Science Foundation of China(Grant No.U2141246).
文摘Artificial intelligence technology is introduced into the simulation of muzzle flow field to improve its simulation efficiency in this paper.A data-physical fusion driven framework is proposed.First,the known flow field data is used to initialize the model parameters,so that the parameters to be trained are close to the optimal value.Then physical prior knowledge is introduced into the training process so that the prediction results not only meet the known flow field information but also meet the physical conservation laws.Through two examples,it is proved that the model under the fusion driven framework can solve the strongly nonlinear flow field problems,and has stronger generalization and expansion.The proposed model is used to solve a muzzle flow field,and the safety clearance behind the barrel side is divided.It is pointed out that the shape of the safety clearance under different launch speeds is roughly the same,and the pressure disturbance in the area within 9.2 m behind the muzzle section exceeds the safety threshold,which is a dangerous area.Comparison with the CFD results shows that the calculation efficiency of the proposed model is greatly improved under the condition of the same calculation accuracy.The proposed model can quickly and accurately simulate the muzzle flow field under various launch conditions.
基金supported by the Program of Humanities and Social Science of Education Ministry of China(Grant No.20YJA630008)the Ningbo Natural Science Foundation of China(Grant No.202003N4142)+1 种基金the Natural Science Foundation of Zhejiang Province,China(Grant No.LY20G010004)the K.C.Wong Magna Fund in Ningbo University,China.
文摘Accurate and real-time passenger flow prediction of rail transit is an important part of intelligent transportation systems(ITS).According to previous studies,it is found that the prediction effect of a single model is not good for datasets with large changes in passenger flow characteristics and the deep learning model with added influencing factors has better prediction accuracy.In order to provide persuasive passenger flow forecast data for ITS,a deep learning model considering the influencing factors is proposed in this paper.In view of the lack of objective analysis on the selection of influencing factors by predecessors,this paper uses analytic hierarchy processes(AHP)and one-way ANOVA analysis to scientifically select the factor of time characteristics,which classifies and gives weight to the hourly passenger flow through Duncan test.Then,combining the time weight,BILSTM based model considering the hourly travel characteristics factors is proposed.The model performance is verified through the inbound passenger flow of Ningbo rail transit.The proposed model is compared with many current mainstream deep learning algorithms,the effectiveness of the BILSTM model considering influencing factors is validated.Through comparison and analysis with various evaluation indicators and other deep learning models,the results show that the R2 score of the BILSTM model considering influencing factors reaches 0.968,and the MAE value of the BILSTM model without adding influencing factors decreases by 45.61%.
基金supported by the Civil Aviation Safety Capacity Building Project.
文摘In order to improve the accuracy and stability of terminal traffic flow prediction in convective weather,a multi-input deep learning(MICL)model is proposed.On the basis of previous studies,this paper expands the set of weather characteristics affecting the traffic flow in the terminal area,including weather forecast data and Meteorological Report of Aerodrome Conditions(METAR)data.The terminal airspace is divided into smaller areas based on function and the weather severity index(WSI)characteristics extracted from weather forecast data are established to better quantify the impact of weather.MICL model preserves the advantages of the convolution neural network(CNN)and the long short-term memory(LSTM)model,and adopts two channels to input WSI and METAR information,respectively,which can fully reflect the temporal and spatial distribution characteristics of weather in the terminal area.Multi-scene experiments are designed based on the real historical data of Guangzhou Terminal Area operating in typical convective weather.The results show that the MICL model has excellent performance in mean squared error(MSE),root MSE(RMSE),mean absolute error(MAE)and other performance indicators compared with the existing machine learning models or deep learning models,such as Knearest neighbor(KNN),support vector regression(SVR),CNN and LSTM.In the forecast period ranging from 30 min to 6 h,the MICL model has the best prediction accuracy and stability.
基金Supported by Universitas Muhammadiyah Yogyakarta,Indonesia and Asia University,Taiwan.
文摘Predicting traffic flow is a crucial component of an intelligent transportation system.Precisely monitoring and predicting traffic flow remains a challenging endeavor.However,existingmethods for predicting traffic flow do not incorporate various external factors or consider the spatiotemporal correlation between spatially adjacent nodes,resulting in the loss of essential information and lower forecast performance.On the other hand,the availability of spatiotemporal data is limited.This research offers alternative spatiotemporal data with three specific features as input,vehicle type(5 types),holidays(3 types),and weather(10 conditions).In this study,the proposed model combines the advantages of the capability of convolutional(CNN)layers to extract valuable information and learn the internal representation of time-series data that can be interpreted as an image,as well as the efficiency of long short-term memory(LSTM)layers for identifying short-term and long-term dependencies.Our approach may utilize the heterogeneous spatiotemporal correlation features of the traffic flowdataset to deliver better performance traffic flow prediction than existing deep learning models.The research findings show that adding spatiotemporal feature data increases the forecast’s performance;weather by 25.85%,vehicle type by 23.70%,and holiday by 14.02%.
基金The authors would like to thank the National Natural Science Foundation of China(61461027)National Natural Science Foundation of China(61465007)for financial support.
文摘According to the time series characteristics of the trajectory history data,we predicted and analyzed the traffic flow.This paper proposed a LSTMXGBoost model based urban road short-term traffic flow prediction in order to analyze and solve the problems of periodicity,stationary and abnormality of time series.It can improve the traffic flow prediction effect,achieve efficient traffic guidance and traffic control.The model combined the characteristics of LSTM(Long Short-Term Memory)network and XGBoost(Extreme Gradient Boosting)algorithms.First,we used the LSTM model that increases dropout layer to train the data set after preprocessing.Second,we replaced the full connection layer with the XGBoost model.Finally,we depended on the model training to strengthen the data association,avoided the overfitting phenomenon of the fully connected layer,and enhanced the generalization ability of the prediction model.We used the Kears based on TensorFlow to build the LSTM-XGBoost model.Using speed data samples of multiple road sections in Shenzhen to complete the model verification,we achieved the comparison of the prediction effects of the model.The results show that the combined prediction model used in this paper can not only improve the accuracy of prediction,but also improve the practicability,real-time and scalability of the model.
基金National Natural Science Foundation of China(No.71961016)Planning Fund for the Humanities and Social Sciences of the Ministry of Education(Nos.15XJAZH002,18YJAZH148)Natural Science Foundation of Gansu Province(No.18JR3RA125)。
文摘Aiming at the problem that some existing traffic flow prediction models are only for a single road segment and the model input data are not pre-processed,a heuristic threshold algorithm is used to de-noise the original traffic flow data after wavelet decomposition.The correlation coefficients of road traffic flow data are calculated and the data compression matrix of road traffic flow is constructed.Data de-noising minimizes the interference of data to the model,while the correlation analysis of road network data realizes the prediction at the road network level.Utilizing the advantages of long short term memory(LSTM)network in time series data processing,the compression matrix is input into the constructed LSTM model for short-term traffic flow prediction.The LSTM-1 and LSTM-2 models were respectively trained by de-noising processed data and original data.Through simulation experiments,different prediction times were set,and the prediction results of the prediction model proposed in this paper were compared with those of other methods.It is found that the accuracy of the LSTM-2 model proposed in this paper increases by 10.278%on average compared with other prediction methods,and the prediction accuracy reaches 95.58%,which proves that the short-term traffic flow prediction method proposed in this paper is efficient.
基金The authors extend their appreciation to the Deanship of Scientific Research at King Khalid University for funding this work through Large Groups Project under grant number(180/43)Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2022R303)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.The authors would like to thank the Deanship of Scientific Research at Umm Al-Qura University for supporting this work by Grant Code:22UQU4340237DSR21.
文摘Intelligent Transportation System(ITS)is one of the revolutionary technologies in smart cities that helps in reducing traffic congestion and enhancing traffic quality.With the help of big data and communication technologies,ITS offers real-time investigation and highly-effective traffic management.Traffic Flow Prediction(TFP)is a vital element in smart city management and is used to forecast the upcoming traffic conditions on transportation network based on past data.Neural Network(NN)and Machine Learning(ML)models are widely utilized in resolving real-time issues since these methods are capable of dealing with adaptive data over a period of time.Deep Learning(DL)is a kind of ML technique which yields effective performance on data classification and prediction tasks.With this motivation,the current study introduces a novel Slime Mould Optimization(SMO)model with Bidirectional Gated Recurrent Unit(BiGRU)model for Traffic Prediction(SMOBGRU-TP)in smart cities.Initially,data preprocessing is performed to normalize the input data in the range of[0,1]using minmax normalization approach.Besides,BiGRUmodel is employed for effective forecasting of traffic in smart cities.Moreover,the novelty of the work lies in using SMO algorithm to effectively adjust the hyperparameters of BiGRU method.The proposed SMOBGRU-TP model was experimentally validated and the simulation results established the model’s superior performance in terms of prediction compared to existing techniques.
基金This research has been supported by the Natural Science Foundation of Hebei Province,China(E2022318002).Thanks are given to Tangsteel Co.,Ltd.of Hesteel Group and Digital Co.,Ltd.of Hesteel Group for providing detailed data,hardware and software support for model development and field production test.
文摘Mathematical(data-driven)models based on state-of-the-art(SOTA)machine learning and deep learning models and data collected from 12,786 heats were established to predict the values of temperature,sample,and carbon(TSC)test,including temperature of molten steel(TSC-Temp),carbon content(TSC-C)and phosphorus content(TSC-P),which made prepa-ration for eliminating the TSC test.To maximize the prediction accuracy of the proposed approach,various models with different inputs were implemented and compared,and the best models were applied to the production process of a Hesteel Group steelmaking plant in China in the field.The number of tabular features(hot metal information,scrap,additives,blowing practices,and preset values)was expanded,and time series(off-gas profiles and blowing practice curves)that could reflect the entire steelmaking process were introduced as inputs.First,the latest machine learning models(LightGBM,CatBoost,TabNet,and NODE)were used to make predictions with tabular features,and the best coefficient of determination R^(2)values obtained for TSC-P,TSC-C and TSC-Temp predictions were 0.435(LightGBM),0.857(Cat-Boost)and 0.678(LightGBM),respectively,which were higher than those of classic models(backpropagation and support vector machine).Then,making predictions was performed by using SOTA time series regression models(SCINet,DLinear,Informer,and MLSTM-FCN)with original time series,SOTA image regression models(NesT,CaiT,ResNeXt,and GoogLeNet)with resized time series,and the proposed Concatenate-Model and Parallel-Model with both tabular features and time series.Through optimization and comparisons,it was finally determined that the Concatenate-Model with MLSTM-FCN,SCINet and Informer as feature extractors performed the best,and its R^(2)values for predicting TSC-P,TSC-C and TSC-Temp reached 0.470,0.858 and 0.710,respectively.Its field test accuracies for TSC-P,TSC-C and TSC-Temp were 0.459,0.850 and 0.685,respectively.A related importance analysis was carried out,and dynamic control methods based on prediction values were proposed.
基金supported in parts by the National Natural Science Foundation of China for Distinguished Young Scholar under Grant 61425012the National Science and Technology Major Projects for the New Generation of Broadband Wireless Communication Network under Grant 2017ZX03001014
文摘The airborne base station(ABS) can provide wireless coverage to the ground in unmanned aerial vehicle(UAV) cellular networks.When mobile users move among adjacent ABSs,the measurement information reported by a single mobile user is used to trigger the handover mechanism.This handover mechanism lacks the consideration of movement state of mobile users and the location relationship between mobile users,which may lead to handover misjudgments and even communication interrupts.In this paper,we propose an intelligent handover control method in UAV cellular networks.Firstly,we introduce a deep learning model to predict the user trajectories.This prediction model learns the movement behavior of mobile users from the measurement information and analyzes the positional relations between mobile users such as avoiding collision and accommodating fellow pedestrians.Secondly,we propose a handover decision method,which can calculate the users' corresponding receiving power based on the predicted location and the characteristic of air-to-ground channel,to make handover decisions accurately.Finally,we use realistic data sets with thousands of non-linear trajectories to verify the basic functions and performance of our proposed intelligent handover controlmethod.The simulation results show that the handover success rate of the proposed method is 8% higher than existing methods.
基金The National Key Research and Development Program of China(No.2019YFB160-0200)the National Natural Science Foundation of China(No.71871011,71890972/71890970)。
文摘To accurately analyze the fluctuation range of time-varying differences in metro-to-bus transfer passenger flows,the application of a probabilistic interval prediction model is proposed to predict transfer passenger flows.First,bus and metro data are processed and matched by association to construct the basis for public transport trip chain extraction.Second,a reasonable matching threshold method to discriminate the transfer relationship is used to extract the public transport trip chain,and the basic characteristics of the trip based on the trip chain are analyzed to obtain the metro-to-bus transfer passenger flow.Third,to address the problem of low accuracy of point prediction,the DeepAR model is proposed to conduct interval prediction,where the input is the interchange passenger flow,the output is the predicted median and interval of passenger flow,and the prediction scenarios are weekday,non-workday,and weekday morning and evening peaks.Fourth,to reduce the prediction error,a combined particle swarm optimization(PSO)-DeepAR model is constructed using the PSO to optimize the DeepAR model.Finally,data from the Beijing Xizhimen subway station are used for validation,and results show that the PSO-DeepAR model has high prediction accuracy,with a 90%confidence interval coverage of up to 93.6%.
文摘Cooperative Intelligent Transport System(C-ITS)plays a vital role in the future road traffic management system.A vital element of C-ITS comprises vehicles,road side units,and traffic command centers,which produce a massive quantity of data comprising both mobility and service-related data.For the extraction of meaningful and related details out of the generated data,data science acts as an essential part of the upcoming C-ITS applications.At the same time,prediction of short-term traffic flow is highly essential to manage the traffic accurately.Due to the rapid increase in the amount of traffic data,deep learning(DL)models are widely employed,which uses a non-parametric approach for dealing with traffic flow forecasting.This paper focuses on the design of intelligent deep learning based short-termtraffic flow prediction(IDL-STFLP)model for C-ITS that assists the people in various ways,namely optimization of signal timing by traffic signal controllers,travelers being able to adapt and alter their routes,and so on.The presented IDLSTFLP model operates on two main stages namely vehicle counting and traffic flow prediction.The IDL-STFLP model employs the Fully Convolutional Redundant Counting(FCRC)based vehicle count process.In addition,deep belief network(DBN)model is applied for the prediction of short-term traffic flow.To further improve the performance of the DBN in traffic flow prediction,it will be optimized by Quantum-behaved bat algorithm(QBA)which optimizes the tunable parameters of DBN.Experimental results based on benchmark dataset show that the presented method can count vehicles and predict traffic flowin real-time with amaximumperformance under dissimilar environmental situations.
文摘In this study, potential of Least Square-Support Vector Regression (LS-SVR) approach is utilized to model the daily variation of river flow. Inherent complexity, unavailability of reasonably long data set and heterogeneous catchment response are the couple of issues that hinder the generalization of relationship between previous and forthcoming river flow magnitudes. The problem complexity may get enhanced with the influence of upstream dam releases. These issues are investigated by exploiting the capability of LS-SVR–an approach that considers Structural Risk Minimization (SRM) against the Empirical Risk Minimization (ERM)–used by other learning approaches, such as, Artificial Neural Network (ANN). This study is conducted in upper Narmada river basin in India having Bargi dam in its catchment, constructed in 1989. The river gauging station–Sandia is located few hundred kilometer downstream of Bargi dam. The model development is carried out with pre-construction flow regime and its performance is checked for both pre- and post-construction of the dam for any perceivable difference. It is found that the performances are similar for both the flow regimes, which indicates that the releases from the dam at daily scale for this gauging site may be ignored. In order to investigate the temporal horizon over which the prediction performance may be relied upon, a multistep-ahead prediction is carried out and the model performance is found to be reasonably good up to 5-day-ahead predictions though the performance is decreasing with the increase in lead-time. Skills of both LS-SVR and ANN are reported and it is found that the former performs better than the latter for all the lead-times in general, and shorter lead times in particular.
基金Project supported by the National Natural Science Foundation of China (Grant No. 62063014)the Natural Science Foundation of Gansu Province, China (Grant No. 22JR5RA365)。
文摘Traffic flow prediction is an effective strategy to assess traffic conditions and alleviate traffic congestion. Influenced by external non-stationary factors and road network structure, traffic flow sequences have macro spatiotemporal characteristics and micro chaotic characteristics. The key to improving the model prediction accuracy is to fully extract the macro and micro characteristics of traffic flow time sequences. However, traditional prediction model by only considers time features of traffic data, ignoring spatial characteristics and nonlinear characteristics of the data itself, resulting in poor model prediction performance. In view of this, this research proposes an intelligent combination prediction model taking into account the macro and micro features of chaotic traffic data. Firstly, to address the problem of time-consuming and inefficient multivariate phase space reconstruction by iterating nodes one by one, an improved multivariate phase space reconstruction method is proposed by filtering global representative nodes to effectively realize the high-dimensional mapping of chaotic traffic flow. Secondly, to address the problem that the traditional combinatorial model is difficult to adequately learn the macro and micro characteristics of chaotic traffic data, a combination of convolutional neural network(CNN) and convolutional long short-term memory(ConvLSTM) is utilized for capturing nonlinear features of traffic flow more comprehensively. Finally,to overcome the challenge that the combined model performance degrades due to subjective empirical determined network parameters, an improved lightweight particle swarm is proposed for improving prediction accuracy by optimizing model hyperparameters. In this paper, two highway datasets collected by the Caltrans Performance Measurement System(PeMS)are taken as the research objects, and the experimental results from multiple perspectives show that the comprehensive performance of the method proposed in this research is superior to those of the prevalent methods.
基金supported by the National Natural Science Foundation of China(No.52125603).
文摘Accurate measurements of physical parameters in a scramjet isolator are very important to promote the design and optimization of the isolator and even the scramjet.In a ground experiment,limited by the inherent characteristics of measurement technology and equipment,it is a big challenge to obtain the velocity field inside an isolator.In this study,a deep learning approach was introduced to combine data obtained from ground experiments and numerical simulations,and a velocity field prediction model was developed for obtaining the velocity field inside an isolator based on experimental Schlieren images.The velocity field prediction model was designed with convolutional neural networks as the main structure.Ground experiments of a scramjet isolator under continuous Mach number variation were carried out,and Schlieren images of the flow field inside the isolator were collected.Numerical simulations of the isolator were also carried out,and the velocity fields inside the isolator under various Mach numbers were obtained.The velocity field prediction model was trained using flow field datasets containing experimental Schlieren images and velocity field,and the mapping relationship between the experimental Schlieren images and the predicted velocity field was successfully established.
文摘The high-resolution(HR)spatio-temporal flow field plays a decisive role in describing the details of the flow field.In the acquisition of the HR flow field,traditional direct numerical simulation(DNS)and other methods face a seriously high computational burden.To address this deficiency,we propose a novel multi-scale temporal path UNet(MST-UNet)model to reconstruct temporal and spatial HR flow fields from low-resolu-tion(LR)flow field data.Different from the previous super-resolution(SR)model,which only takes advantage of LR flow field data at instantaneous(SLR)or in a time-series(MTLR),MST-UNet introduces multi-scale information in both time and space.MST-UNet takes the LR data at the current frame and the predicted HR result at the previous moment as the model input to complete the spatial SR reconstruction.On this basis,a temporal model is introduced as the inbetweening model to obtain HR flow field data in space and time to complete spatio-temporal SR reconstruction.Finally,the proposed model is validated by the spatio-temporal SR task of the flow field around two-dimen-sional cylinders.Experimental results show that the outcome of the MST-UNet model in spatial SR tasks is much better than those of SLR and MTLR,which can greatly improve prediction accuracy.In addition,for the spatio-temporal SR task,the spatio-temporal HR flow field predicted by the MST-UNet model has higher accuracy either.
基金the National Natural Science Foundation of China(No.61905178)the Science&Technology Development Fund of Tianjin Education Commission for Higher Education(No.2019KJ021)the Natural Science Foundation of Tianjin(No.18JCQNJC71100)。
文摘Phase unwrapping is one of the key roles in fringe projection three-dimensional(3D)measurement technology.We propose a new method to achieve phase unwrapping in camera array light filed fringe projection 3D measurement based on deep learning.A multi-stream convolutional neural network(CNN)is proposed to learn the mapping relationship between camera array light filed wrapped phases and fringe orders of the expected central view,and is used to predict the fringe order to achieve the phase unwrapping.Experiments are performed on the light field fringe projection data generated by the simulated camera array fringe projection measurement system in Blender and by the experimental 3×3 camera array light field fringe projection system.The performance of the proposed network with light field wrapped phases using multiple directions as network input data is studied,and the advantages of phase unwrapping based on deep learning in light filed fringe projection are demonstrated.
基金supported by the Strategic Priority Research Program of the Chinese Academy of Sciences [grant number XDA 19060102]supported by the National Natural Science Foundation of China[grant number 42030410]+2 种基金the Laoshan Laboratory [grant number LSL202202402]the Strategic Priority Research Program of the Chinese Academy of Sciences [grant number XDB40000000]the Startup Foundation for Introducing Talent of NUIST
